Spoken Language Identification Using Hybrid Feature Extraction Methods

TL;DR

This study explores hybrid feature extraction methods combining MFCC, PLP, BFCC, and RPLP for spoken language identification, demonstrating improved accuracy over traditional features using VQ-DTW and GMM classifiers.

Contribution

It introduces hybrid feature extraction techniques for LID and compares their effectiveness with conventional methods, highlighting BFCC and RPLP as superior features.

Findings

Hybrid features outperform conventional features in language identification accuracy.

BFCC shows better performance than MFCC across classifiers.

RPLP combined with GMM yields the highest identification performance.

Abstract

This paper introduces and motivates the use of hybrid robust feature extraction technique for spoken language identification (LID) system. The speech recognizers use a parametric form of a signal to get the most important distinguishable features of speech signal for recognition task. In this paper Mel-frequency cepstral coefficients (MFCC), Perceptual linear prediction coefficients (PLP) along with two hybrid features are used for language Identification. Two hybrid features, Bark Frequency Cepstral Coefficients (BFCC) and Revised Perceptual Linear Prediction Coefficients (RPLP) were obtained from combination of MFCC and PLP. Two different classifiers, Vector Quantization (VQ) with Dynamic Time Warping (DTW) and Gaussian Mixture Model (GMM) were used for classification. The experiment shows better identification rate using hybrid feature extraction techniques compared to conventional feature extraction methods.BFCC has shown better performance than MFCC with both classifiers. RPLP along with GMM has shown best identification performance among all feature extraction techniques.